SEMI-SUPERVISED INCREMENTAL LEARNING OF HIERARCHICAL APPEARANCE MODELS

We propose an incremental learning scheme for learning a class hierarchy for objects typically occurring multiple in images. Given one example of an object that appears several times in the image, e.g. is part of a repetitive structure, we propose a method for identifying prototypes using an unsupervised clustering procedure. These prototypes are used for building a hierarchical appearance based model of the envisaged class in a supervised manner. For classification of new instances detected in new images we use linear subspace methods that combine discriminative and reconstructive properties. The used methods are chosen to be capable for an incremental update. We test our approach on facade images with repetitive windows and balconies. We use the learned object models to find new instances in other images, e. g. the neighbouring facade and update already learned models with the new instances.

[1]  Horst Bischof,et al.  Why to Combine Reconstructive and Discriminative Information for Incremental Subspace Learning , 2006 .

[2]  Gang Wang,et al.  OPTIMOL: automatic Online Picture collecTion via Incremental MOdel Learning , 2007, CVPR.

[3]  Andrew Zisserman,et al.  Video Google: Efficient Visual Search of Videos , 2006, Toward Category-Level Object Recognition.

[4]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[5]  Allen Y. Yang,et al.  Symmetry-based 3-D reconstruction from perspective images , 2005, Comput. Vis. Image Underst..

[6]  Joachim M. Buhmann,et al.  A maximum entropy approach to pairwise data clustering , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[7]  Sanja Fidler,et al.  Combining reconstructive and discriminative subspace methods for robust classification and regression by subsampling , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[9]  Joachim M. Buhmann,et al.  Pairwise Data Clustering by Deterministic Annealing , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Allen Y. Yang,et al.  On Symmetry and Multiple-View Geometry: Structure, Pose, and Calibration from a Single Image , 2004, International Journal of Computer Vision.

[11]  Luc Van Gool,et al.  Towards mass-produced building models , 2007 .

[12]  Horst Bischof,et al.  Incremental LDA Learning by Combining Reconstructive and Discriminative Approaches , 2007, BMVC.

[13]  W. Cao,et al.  The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. XXXVIII-4/C7 CLASSIFICATION OF HIGH RESOLUTION OPTICAL AND SAR FUSION IMAGE USING FUZZY KNOWLEDGE AND OBJECT-ORIENTED PARADIGM , 2010 .